NVIDIA B300 vs PNY A100 Liquid Cooled

Comparison of NVIDIA B300 with 144 GB HBM3e and 18,944 cores vs PNY A100 Liquid Cooled with 80 GB HBM2e and 6,912 cores.

Loading...

Performance Rating

NVIDIA B300 outperforms PNY A100 Liquid Cooled by 180.65% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA B300

71.9

NVIDIA B300

71.9
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

PNY A100 Liquid Cooled

25.6

PNY A100 Liquid Cooled

25.6

Contents:

Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Additional

Memory

Memory Size

🔥 +80% 144 ГБ ×2 (288 ГБ)
80 GB

Memory Type

HBM3e HBM2e

Memory Bandwidth

🔥 +111% 4.10 TB/s ×2 (8.2 TB/s)
1.94 TB/s

Memory Bus Width

4,096 бит ×2 (8192 бит) 5,120 бит

ML Performance

FP16 (Half Precision)

1.2318 TFLOPS
🔥 +6,230% 77.97 TFLOPS

BF16 (Brain Float)

No
🔥 311.84 TFLOPS

TF32 (TensorFloat)

No
🔥 155.92

Compute Power

FP32 (Single Precision)

🔥 +295% 76.99 TFLOPS
19.49 TFLOPS

FP64 (Double Precision)

1.2029 TFLOPS
🔥 +710% 9.746 TFLOPS

CUDA Cores

🔥 +174% 18,944 ×2 (37888)
6,912

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Blackwell Ultra Ampere

SM (Streaming Multiprocessor)

🔥 +37% 148
108

PCIe Version

PCIe 5.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

🔥 10.3
8.0

Clocks & Performance

Base Clock

🔥 +56% 1,665
1,065

Boost Clock

🔥 +44% 2,032
1,410

Memory Clock

🔥 +32% 2,000
1,512

Power Consumption

Recommended PSU

1800 W
🔥 -61% 700 W

Power Connector

No 8-pin EPS

TDP/TGP

1400 W
🔥 -79% 300 W

Rendering

Texture Units (TMU)

🔥 +37% 592 ×2 (1184)
432

ROP

No No

L2 Cache

50 MB
🔥 +60% 80 MB

Additional

Slots

🔥 SXM Module
Single-slot

Release Date

Sept. 11, 2025 June 28, 2021

Display Outputs

No outputs
No outputs

Renting is cheaper than buying